Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
The extension fault isolation fix means a single broken extension no longer silently degrades an entire Spec Kit run, improving reliability for projects with multiple extensions.
The long-thread resume optimization and signal-drain correctness fixes directly address reliability and cost bottlenecks in stateful, multi-turn agent workflows built on Mastra.
The release resolves multiple Agent Manager stability regressions — including a webview blanking bug and startup conflicts with other VS Code extensions — while the BYOK badge makes key-routing transparency visible directly in the model selector.
Record & Replay removes the need to manually re-describe recurring workflows in prompts by encoding a user's demonstrated process and preferences into a persistent, reusable skill.
The auto-mode safety guardrails directly prevent the agent from executing irreversible git and infrastructure teardown operations without explicit user intent, reducing the risk of accidental data or state loss during autonomous sessions.
Artifacts replaces static session exports with auto-refreshing, session-aware pages that teams can view collaboratively through a private organizational link.
The release introduces a user-owned, local-first memory layer that persists AI agent context across sessions and tools, directly addressing the session-reset limitation that causes repeated re-explanation of architectural decisions in tools like Claude Code and Cursor.
The addition of GitHub and Slack triggers alongside computer use support expands Cursor Automations beyond its previous trigger set, enabling agents to respond to a broader range of external events.
Kimi K2.7 Code delivers substantial benchmark improvements over its predecessor while cutting reasoning token usage by 30%, making a capable open-weights coding model more efficient and freely accessible.
MAI-Code-1-Flash's expansion brings Microsoft's small coding model to more Copilot entry points, widening the surfaces where developers can select it as their model of choice.